Self-Referential Meta Learning

Louis Kirsch, Jürgen Schmidhuber

Abstract: Meta Learning automates the search for learning algorithms. At the same time, it creates a dependency on human engineering on the meta-level, where meta learning algorithms need to be designed. In this paper, we investigate self-referential meta learning systems that modify themselves without the need for explicit meta optimization. We discuss the relationship of such systems to memory-based meta learning and show that self-referential neural networks require functionality to be reused in the form of parameter sharing. Finally, we propose Fitness Monotonic Execution (FME), a simple approach to avoid explicit meta optimization. A neural network self-modifies to solve bandit and classic control tasks, improves its self-modifications, and learns how to learn, purely by assigning more computational resources to better performing solutions.

Keywords: meta-learning, self-referential, self-modification, meta-optimization, reinforcement-learning

One-sentence Summary: We investigate self-referential meta learning systems that modify themselves without the need for explicit meta optimization.

Reproducibility Checklist: Yes

Broader Impact Statement: Yes

Paper Availability And License: Yes

Code Of Conduct: Yes

Reviewers: Louis Kirsch, [e-mail]